Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.1810. Min Act: -0.1700
Data Index: 8529655 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.1185. Min Act: -0.1699
Data Index: 1877893 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.1185. Min Act: -0.1700
Data Index: 6265633 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0873. Min Act: -0.1700
Data Index: 3511280 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0248. Min Act: -0.1700
Data Index: 6492255 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0560. Min Act: -0.1700
Data Index: 1005415 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1810. Min Range: -5.1810
Max Act: 4.9935. Min Act: -0.1700
Data Index: 6154925 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0560. Min Act: -0.1700
Data Index: 5479159 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0560. Min Act: -0.1700
Data Index: 5283662 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0248. Min Act: -0.1700
Data Index: 2415693 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0248. Min Act: -0.1700
Data Index: 5010595 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0248. Min Act: -0.1700
Data Index: 2248489 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0560. Min Act: -0.1700
Data Index: 4464073 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0560. Min Act: -0.1700
Data Index: 8613989 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0560. Min Act: -0.1700
Data Index: 851272 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0560. Min Act: -0.1700
Data Index: 5074039 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0248. Min Act: -0.1700
Data Index: 4797264 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1810. Min Range: -5.1810
Max Act: 5.0248. Min Act: -0.1700
Data Index: 4699744 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1810. Min Range: -5.1810
Max Act: 4.9935. Min Act: -0.1700
Data Index: 805910 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1810. Min Range: -5.1810
Max Act: 4.9935. Min Act: -0.1700
Data Index: 1847208 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19